{"id":"https://openalex.org/W3096893582","doi":"https://doi.org/10.21437/interspeech.2020-2205","title":"Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation","display_name":"Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096893582","doi":"https://doi.org/10.21437/interspeech.2020-2205","mag":"3096893582"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2205","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100373491","display_name":"Jingjing Chen","orcid":"https://orcid.org/0000-0003-1737-3420"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Chen","raw_affiliation_strings":["School of Computer Science and Communication Engineering, Jiangsu University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068470372","display_name":"Qirong Mao","orcid":"https://orcid.org/0000-0002-0616-4431"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qirong Mao","raw_affiliation_strings":["Jiangsu Engineering Research Center of big data ubiquitous perception and intelligent agriculture applications, Zhenjiang, China","School of Computer Science and Communication Engineering, Jiangsu University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu Engineering Research Center of big data ubiquitous perception and intelligent agriculture applications, Zhenjiang, China","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100407412","display_name":"Dong Liu","orcid":"https://orcid.org/0000-0002-2286-5756"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Liu","raw_affiliation_strings":["School of Computer Science and Communication Engineering, Jiangsu University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Communication Engineering, Jiangsu University, China","institution_ids":["https://openalex.org/I115592961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I115592961"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":311,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2642","last_page":"2646"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.980400025844574,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7451445460319519},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.6838427186012268},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6049364805221558},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5414377450942993},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4799419045448303},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37703007459640503},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.23158231377601624},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19016924500465393},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.17098680138587952},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06556850671768188}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7451445460319519},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.6838427186012268},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6049364805221558},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5414377450942993},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4799419045448303},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37703007459640503},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.23158231377601624},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19016924500465393},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.17098680138587952},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06556850671768188},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2205","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W80444264","https://openalex.org/W185399533","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1555814299","https://openalex.org/W2143169494","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2800022361","https://openalex.org/W2800664709","https://openalex.org/W2891405874","https://openalex.org/W2902458453","https://openalex.org/W2952218014","https://openalex.org/W2955805055","https://openalex.org/W2962715207","https://openalex.org/W2962905190","https://openalex.org/W2962935966","https://openalex.org/W2964089206","https://openalex.org/W2972460025","https://openalex.org/W2972767900","https://openalex.org/W2972853597","https://openalex.org/W2973054567","https://openalex.org/W2973143779","https://openalex.org/W2981976899","https://openalex.org/W3015199127","https://openalex.org/W3015794161","https://openalex.org/W3124666641","https://openalex.org/W3185109982","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1518859147","https://openalex.org/W1974981856","https://openalex.org/W1983045063","https://openalex.org/W2045506488","https://openalex.org/W4321794819","https://openalex.org/W2072124114","https://openalex.org/W2401567014","https://openalex.org/W2889698889"],"abstract_inverted_index":{"The":[0],"dominant":[1],"speech":[2,16,50,60,68,80,96,124],"separation":[3,37],"models":[4],"are":[5],"based":[6],"on":[7,20,128,142],"complex":[8],"recurrent":[9,31,104],"or":[10],"convolution":[11],"neural":[12,32,105],"network":[13,46,106],"that":[14,132],"model":[15,77,119],"sequences":[17,69,81,97],"indirectly":[18],"conditioning":[19],"context,":[21],"such":[22],"as":[23],"passing":[24],"information":[25,93],"through":[26],"many":[27],"intermediate":[28],"states":[29],"in":[30,56,67,87],"network,":[33],"leading":[34],"to":[35],"suboptimal":[36],"performance.In":[38],"this":[39],"paper,":[40],"we":[41],"propose":[42],"a":[43,63,103],"dual-path":[44],"transformer":[45,86],"(DPT-Net)":[47],"for":[48,59,78,121],"end-to-end":[49],"separation,":[51],"which":[52,73],"introduces":[53,62],"direct":[54,83],"context-awareness":[55],"the":[57,79,91,95,108,112,136,143],"modeling":[58],"sequences.By":[61],"improved":[64,85],"transformer,":[65],"elements":[66],"can":[70,76],"interact":[71],"directly,":[72],"enables":[74],"DPTNet":[75],"with":[82],"context-awareness.The":[84],"our":[88,118,133],"approach":[89,134],"learns":[90],"order":[92],"of":[94,114],"without":[98],"positional":[99],"encodings":[100],"by":[101],"incorporating":[102],"into":[107],"original":[109],"transformer.In":[110],"addition,":[111],"structure":[113],"dual":[115],"paths":[116],"makes":[117],"efficient":[120],"extremely":[122],"long":[123],"sequence":[125],"modeling.Extensive":[126],"experiments":[127],"benchmark":[129],"datasets":[130],"show":[131],"outperforms":[135],"current":[137],"state-of-the-arts":[138],"(20.6":[139],"dB":[140],"SDR":[141],"public":[144],"WSj0-2mix":[145],"data":[146],"corpus).":[147]},"counts_by_year":[{"year":2026,"cited_by_count":23},{"year":2025,"cited_by_count":62},{"year":2024,"cited_by_count":44},{"year":2023,"cited_by_count":77},{"year":2022,"cited_by_count":76},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}